AAAI 2025technical0 citations
Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification (Student Abstract)
Shovito Barua Soumma, Abdullah Mamun, Hassan Ghasemzadeh
Abstract
FuSE-MET addresses critical challenges in deploying human activity recognition (HAR) systems in uncontrolled environments by effectively managing noisy labels, sparse data, and undefined activity vocabularies. By integrating BERT-based word embeddings with domain-specific knowledge (i.e., MET values), FuSE-MET optimizes label merging, reducing label complexity and improving classification accuracy. Our approach outperforms the state-of-the-art techniques, including ChatGPT-4, by balancing semantic meaning and physical intensity.
BibTeX
@article{Soumma_Mamun_Ghasemzadeh_2025, title={Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification (Student Abstract)}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35301}, DOI={10.1609/aaai.v39i28.35301}, abstractNote={FuSE-MET addresses critical challenges in deploying human activity recognition (HAR) systems in uncontrolled environments by effectively managing noisy labels, sparse data, and undefined activity vocabularies. By integrating BERT-based word embeddings with domain-specific knowledge (i.e., MET values), FuSE-MET optimizes label merging, reducing label complexity and improving classification accuracy. Our approach outperforms the state-of-the-art techniques, including ChatGPT-4, by balancing semantic meaning and physical intensity.}, number={28}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Soumma, Shovito Barua and Mamun, Abdullah and Ghasemzadeh, Hassan}, year={2025}, month={Apr.}, pages={29495-29497} }